The Impact of Age on Predictive Performance of National Early Warning Score at Arrival to Emergency Departments: Development and External Validation.

Abstract

To investigate how age affects the predictive performance of the National Early Warning Score (NEWS) at arrival to the emergency department (ED) regarding inhospital mortality and intensive care admission. International multicenter retrospective cohorts from 2 Danish and 3 Dutch ED. Development cohort: 14,809 Danish patients aged ≥18 years with at least systolic blood pressure or pulse measured from the Danish Multicenter Cohort. External validation cohort: 50,448 Dutch patients aged ≥18 years with all vital signs measured from the Netherlands Emergency Department Evaluation Database (NEED). Multivariable logistic regression was used for model building. Performance was evaluated overall and within age categories: 18 to 64 years, 65 to 80 years, and more than 80 years. In the Danish Multicenter Cohort, a total of 2.5% died inhospital, and 2.8% were admitted to the ICU, compared with 2.8% and 1.6%, respectively, in the NEED. Age did not add information for the prediction of intensive care admission but was the strongest predictor for inhospital mortality. For NEWS alone, severe underestimation of risk was observed for persons above 80 while overall Area Under Receiver Operating Characteristic (AUROC) was 0.82 (confidence interval [CI] 0.80 to 0.84) in the Danish Multicenter Cohort versus 0.75 (CI 0.75 to 0.77) in the NEED. When combining NEWS with age, underestimation of risks was eliminated for persons above 80, and overall AUROC increased significantly to 0.86 (CI 0.85 to 0.88) in the Danish Multicenter Cohort versus 0.82 (CI 0.81 to 0.83) in the NEED. Combining NEWS with age improved the prediction performance regarding inhospital mortality, mostly for persons aged above 80, and can potentially improve decision policies at arrival to EDs.